People are using AI to make their smart TVs dumb again
Fed up with ads, tracking and sluggish interfaces, some smart TV owners are turning to AI agents to strip away bloatware and take back control of their TVs.
TechBrief — تازهترین اخبار فناوری
آخرین خبرها
All-Clad Factory Seconds Sale: Cookware Deals for Fall Cooking
Upgrade your cold-weather cooking setup with discounted cookware for soups, stews, and roasts.
Apple teases MacBook Pro event next week
Apple has sent invites to a second product launch this month, and it's scheduled for October 28th at 1PM ET in Los Angeles. At the event, Apple is set to announce new Macs and a refreshed iPad Mini, according to Bloomberg. The big announcement is expected to be a new MacBook Pro with an OLED […]
AI companies are coming for the plumbers
Comments URL: https://news.ycombinator.com/item?id=50154060
Points: 20
# Comments: 14
Launch HN: Laminar (YC S24) – We trained a model to catch silent agent failures
Hi HN, we’re Robert and Din from Laminar (https://laminar.sh). We’ve been building open-source observability for AI agents since 2024. Recently, we released flow-1, a model trained with RL to find errors in agent traces. On our benchmark (https://laminar.sh/blog/flow-1), it matches GPT-6-sol in detection quality while being 23x cheaper. This makes it affordable to analyze every production agent trace, without sampling.
Here’s a one-minute walkthrough: https://youtu.be/KJa3h6ZJNLQ
We also put together a post with example traces and analyses from flow-1 and other models: https://laminar.sh/blog/flow-1-in-action
Agent observability is crowded, so instead of a bullet list of how Laminar differs from X, we’ll explain how we’re solving agent observability from first principles.
Agents now run for many steps and fail implicitly. An agent can click the wrong button or cite the wrong document while every call completes successfully. These errors are the most useful ones to catch and understand. To find them, you need to understand what the agent was trying to do and inspect its LLM calls and tool results. Simply looking at the final agent output is not enough.
Collecting traces alone doesn’t solve this. A lot of agent observability platforms are still data collectors at their core. You can end up paying to store traces that nobody has time to read or extract value from.
Using another LLM to inspect traces is THE solution, but capable models are expensive at scale and cheaper ones often miss errors or flag unrelated things.
So we built our model to solve exactly this problem. We finetuned a small OSS model and then post trained it with RL on thousands of synthetic investigations of realistic agent workflows in software, legal, customer support, etc. We got a model that is both good at agent trace analysis and very cheap to run.
flow-1 runs inside a harness we call Signals. It acts as a coding agent, treating an agent trace like a repo, with each span (an LLM call, tool call, etc.) as a file. It starts from a compressed string representation of a full agent trace and a user prompt, then greps across spans and reads the relevant ones in full.
The beauty of Signals is that it can respond to a general prompt. You can ask it to identify user frustration, check whether your browser agent completed a checkout, and so on. It’s not limited to raw error detection. It returns findings as JSON in a schema users can freely define. We call these signal events.
Once you’re analyzing every trace, you also have too many individual events to read. That’s why we automatically group similar signal events into clusters. You can see recurring problems and how often they happen, then drill into individual events and the traces behind them.
You can use traces from a cluster to build an eval dataset for that type of failure. You can then use your favourite coding agent to hillclimb on those evals and check that the fix works across these cases before shipping it to prod.
Trace → analyze → catch errors and form clusters → fix → release. Making this loop easy is why we built Laminar.
We’ve put the same thought into the rest of Laminar. Our blog (https://laminar.sh/blog) explains how looking closely at how agents actually work led us to build 20x trace compression, a custom SQL query engine and automatic task extraction.
Laminar is Apache 2.0 and self-hostable (https://github.com/lmnr-ai/lmnr). We make money from the managed cloud.
We’d love to hear how you track your agents’ performance today. How much do you learn from user feedback versus your own monitoring? And when you fix something, how do you check that it hasn’t introduced a different failure?
Comments URL: https://news.ycombinator.com/item?id=50154029
Points: 7
# Comments: 0
WhatsApp Help Pages Leaked Hidden Instructions for a Meta Chatbot
Around 80 pages on WhatsApp’s website exposed instructions that were designed for its chatbot, including “WHAT NOT TO SAY.” Meta says a bug caused the issue.
Another day another GitHub incident
Article URL: https://www.githubstatus.com/incidents/8tzbpcnl75jp
Comments URL: https://news.ycombinator.com/item?id=50153934
Points: 48
# Comments: 19
JB Pritzker thinks AI could help us live to 100 — or threaten us like nukes
Today, I’m talking with Illinois Gov. JB Pritzker, who has a lot of thoughts about AI, tech, and privacy. If you’ve been listening to the show, you know that one of my running theories is that those issues are driving a big and maybe kind of unexpected political realignment — and with the midterms coming […]
Amazon is funding a new nuclear plant in Indiana
Amazon has signed an agreement with X-energy and American Electric Power (AEP) to fund the building of a new nuclear energy facility in Indiana. The proposed plant, which would replace the now defunct coal-fueled Breed Generating Station in Fairbanks, Sullivan County, aims to provide up to 960 megawatts of carbon-free energy for both the regional […]
Nvidia launches new open models to run agents in the enterprise and on PCs
Nvidia is leaning hard into the trend of enterprise companies wanting to run their own open models in their own data centers and also trying to make on-device, private AI agents a thing.